Offline Meta Reinforcement Learning with In-Distribution Online Adaptation.
Jianhao WangJin ZhangHaozhe JiangJunyu ZhangLiwei WangChongjie ZhangPublished in: ICML (2023)
Keyphrases
- reinforcement learning
- real time
- online learning
- spatial distribution
- adaptation process
- learning algorithm
- function approximation
- robotic control
- database
- multi agent reinforcement learning
- reinforcement learning algorithms
- temporal difference
- meta level
- multi agent
- learning problems
- gaussian distribution
- markov decision processes
- optimal policy
- state space
- temporal difference learning
- information retrieval
- machine learning
- data sets